© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 16694
    Prev
    Next
    INDEX
    Explanations

    effects and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     correlates
    -0.11
     lif
    -0.10
     åĮ
    -0.10
     overt
    -0.09
    upo
    -0.09
    _bias
    -0.09
     indu
    -0.09
    Loss
    -0.09
     correl
    -0.09
    data
    -0.09
    POSITIVE LOGITS
     effect
    0.16
     med
    0.14
     relationships
    0.14
     effects
    0.14
     pars
    0.13
     explaining
    0.13
     explained
    0.12
    æķĪæŀľ
    0.12
     ìĦ¤ëªħ
    0.12
    説æĺİ
    0.12
    Activations Density 0.069%

    No Known Activations